Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/realistsec/mpa-first-guidelines/copilot-instructionsgit clone --depth 1 https://github.com/RealistSec/mpa-first-guidelinesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/realistsec/mpa-first-guidelines/copilot-instructions)<a href="https://agentmods.dev/instructions/realistsec/mpa-first-guidelines/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/realistsec/mpa-first-guidelines/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01197 | $0.01197 |
| Opus 5 | $0.00598 | $0.00598 |
| Sonnet 5 | $0.00239 | $0.00239 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
mpa-first-guidelines copilot-instructions.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions: MPA-First Guidelines Repository
Repository Purpose
This is a reference documentation repository containing MPA (Multi-Page Application) development guidelines for AI coding agents. Users copy these guidelines into their own projects to teach AI tools (GitHub Copilot, Cursor, Claude, Codex, etc.) to generate MPA-first code instead of defaulting to SPA frameworks.
Key Files & Their Roles
Base rule files:
-
mpa-rules.md- Comprehensive, strict MPA-first mandate with strict PHP & vanilla JS only. This is the primary reference document. -
mpa-relaxed-rules.md- Variant ruleset allowing full use of PHP & jQuery for progressive enhancement while maintaining MPA architecture.
Assistant-specific base instruction files:
-
.github/agents/mpa-strict-agent.md- Copilot agent-specific instructions file based onmpa-rules.mdfor strict MPA adherence. -
.github/agents/mpa-relaxed-agent.md- Copilot agent-specific instructions file based onmpa-relaxed-rules.mdfor a more lenient MPA approach.
Documentation:
README.md- User-facing documentation explaining the problem, solution, and how to integrate these rules into AI coding workflows.
Writing Style & Tone
When editing these guidelines:
- Be authoritative and prescriptive - Use "MUST" and "DO NOT" language. These are rules, not suggestions.
- Provide concrete examples - Every principle should have a code snippet showing the correct pattern.
- Explain the "why" - Help developers understand the philosophy, not just the mechanics.
- Stay opinionated - The entire premise is rejecting the SPA-default paradigm. Don't hedge or equivocate.
Content Maintenance Patterns
Adding New Rules or Sections
- Keep examples realistic - Use patterns that would appear in actual projects
- Maintain parallelism - Both
mpa-rules.*with.github/agents/mpa-strict-agent.mdandmpa-relaxed-rules.*with.github/agents/mpa-relaxed-agent.mdshould cover the same topics in the same order - Update the table of contents - If you add major sections, ensure navigation is clear
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 96 lines · 1,197 tokens per session scan A 734bf27da400
mpa-first-guidelines copilot-instructions.md is an instructions file published in the GitHub repository RealistSec/mpa-first-guidelines (10 stars, last pushed 9mo ago), licensed MIT. It adds 1,197 tokens to every session, about $0.0060 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
healthcare-agents AGENTS.md
Instructions for ajhcs/healthcare-agents, covering healthcare agents repository instructions, repository map, git workflow and self-improvement loop.
angular-material-ai-rules copilot-instructions.md
Instructions for Angular-Material-Dev/angular-material-ai-rules, covering angular material 20 copilot instructions, persona, core principles for copilot ai agents, project best practices and 1. styling and theming.
skillkit CLAUDE.md
Instructions for sacredvoid/skillkit, covering skillkit, github pages, skill file format and git remote.
agent-context-doctor AGENTS.md
AGENTS.md instructions for dadion123/agent-context-doctor, covering agent notes, commands, product direction and maintainer workflow.
agent-context-doctor CLAUDE.md
Claude Code instructions for dadion123/agent-context-doctor: Read AGENTS.md first. This file is a thin Claude Code adapter so the repository has one canonical agent context.
agent-context-doctor copilot-instructions.md
Copilot instructions for dadion123/agent-context-doctor: Use AGENTS.md as the canonical repository context.